EEMNet: an end-to-end efficient model for PCB surface tiny defect detection

The miniaturization of electronic products has led to the denser and more crowded wiring on printed circuit boards (PCBs), which has made PCB defects smaller and more difficult to detect. Moreover, the complex morphology of PCB defects highlights the importance of capturing their contextual information for improved detection accuracy and efficiency. While CNN can effectively capture local information, its layered convolution-based feature extraction method has limitations in capturing contextual information. The transformer structure can capture long-range dependencies effectively, but at the cost of increased computational effort. To address this issue, an end-to-end efficient model (EEMNet) for PCB surface tiny defect detection is proposed, leveraging the modularity idea. This model includes a novel and efficient attention mechanism that can capture global dependencies without adding too much computational effort, along with several plug-and-play modules for enhancing tiny defect features. The model also incorporates a scale-sensitive localization loss function and makes extensive use of Ghost convolution to substantially reduce the number of model parameters. The resulting EEMNet achieves a detection accuracy of 99.1\(\%\) and a detection speed of 77 FPS on a published PCB dataset, outperforming existing PCB detection algorithms. Overall, the proposed model provides an efficient and effective solution for PCB tiny defect detection.